def get_references(current_file):
result = {}
with open(current_file, 'rb') as fp:
message = pyzmail.message_from_file(fp)
if 'Message-Id' in message.keys():
result['message-id'] = message['Message-Id']
elif 'Message-ID' in message.keys():
result['message-id'] = message['Message-ID']
else:
logging.warn('no message id in file %s', current_file)
if 'References' in message.keys():
references = message['References'].split(' ')
result['references'] = references
return result
def ExtractSubPayload(filename):
''' Extract the subject and payload from the .eml file.
'''
if not os.path.exists(filename): # dest path doesnot exist
print("ERROR: input file does not exist:" + filename)
os.exit(1)
fp = open(filename)
msg = pyzmail.message_from_file(fp)
payload = ""
if msg.html_part != None:
payload = msg.html_part.get_payload()
payload = str(payload)
# print payload
return payload
def ExtractSubPayload(filename):
''' Extract the subject and payload from the .eml file.
'''
if not os.path.exists(filename): # dest path doesnot exist
print("ERROR: input file does not exist:" + filename)
os.exit(1)
fp = open(filename)
msg = pyzmail.message_from_file(fp)
payload1 = ""
if msg.text_part != None:
msg1 = msg.text_part.get_payload()
#payload1=msg1.decode('utf-8')
payload1 = str(msg1)
#print payload1
return payload1
def get_references(current_file):
result = {}
with open(current_file, 'rb') as fp:
message = pyzmail.message_from_file(fp)
if 'Message-Id' in message.keys():
result['message-id'] = message['Message-Id']
elif 'Message-ID' in message.keys():
result['message-id'] = message['Message-ID']
elif 'Message-id' in message.keys():
result['message-id'] = message['Message-id']
else:
logging.warn('no message id in file %s', current_file)
logging.info([key for key in message.keys()])
if 'References' in message.keys():
references = message['References'].split(' ')
result['references'] = references
if 'In-Reply-To' in message.keys():
result['in-reply-to'] = message['In-Reply-To']
return result, message
def filter_file_by_content(arg_file_name, arg_senders):
with open(arg_file_name, 'rb') as fp:
message = pyzmail.message_from_file(fp)
# todo clean up internal whitespace
senders = message.get_addresses('from')
clean_senders = [clean_address(item[1]) for item in senders]
if len(set(clean_senders) & arg_senders) != 0:
return None
text_part = message.text_part
if text_part is not None:
charset = text_part.charset
payload = text_part.get_payload()
if charset is not None:
try:
body = payload.decode(charset,
'ignore').encode(target_encoding)
except LookupError as lookupError:
if text_part.charset == 'iso-8859-8-i':
body = payload.decode('iso-8859-8',
'ignore').encode(target_encoding)
else:
body = payload.decode('utf-8',
'ignore').encode(target_encoding)
logging.warn('lookup error %s', lookupError)
else:
body = payload.decode('utf-8',
'ignore').encode(target_encoding)
body_ascii = body.decode('utf-8',
'ignore').encode('ascii', 'ignore')
return body_ascii
else:
return None
os.makedirs(output_folder)
if not str(output_folder).endswith('/'):
output_folder += '/'
target_encoding = 'utf-8'
for item in os.listdir(input_folder):
logging.debug(item)
if path.isdir(input_folder + item):
output_subfolder = output_folder + item + '/'
logging.debug(output_subfolder)
if not os.path.exists(output_subfolder):
os.makedirs(output_subfolder)
for current_file in os.listdir(input_folder + item):
logging.debug(current_file)
with open(input_folder + item + '/' + current_file, 'rb') as fp:
message = pyzmail.message_from_file(fp)
text_part = message.text_part
if text_part is not None:
charset = text_part.charset
payload = text_part.get_payload()
if charset is not None:
try:
result = payload.decode(
charset, 'ignore').encode(target_encoding)
except LookupError as lookupError:
if text_part.charset == 'iso-8859-8-i':
result = payload.decode(
'iso-8859-8',
'ignore').encode(target_encoding)
else:
result = payload.decode(
def get_json(self, current_file, arg_process_text_part, arg_process_html_part, arg_process_both_empty,
arg_kmeans_cluster_dictionary):
result = {'original_file': current_file}
with open(current_file, 'rb') as fp:
message = pyzmail.message_from_file(fp)
# todo clean up internal whitespace
senders = message.get_addresses('from')
result['sender'] = [item[i] for i in [0, 1] for item in senders]
result['short_sender'] = [item.split('@')[0] for item in result['sender']]
clean_senders = [self.clean_address(item[1]) for item in senders]
result['clean_sender'] = clean_senders
# todo clean up internal whitespace
recipients = message.get_addresses('to') + message.get_addresses('cc') + message.get_addresses('bcc')
result['recipient'] = recipients
result['party'] = list(
['{name} = {address}'.format(name=item[0], address=item[1]) for item in senders + recipients])
result['clean_recipient'] = [self.clean_address(item[1]) for item in recipients]
result['recipient'] = [item[i] for i in [0, 1] for item in recipients]
result['short_recipient'] = [item.split('@')[0] for item in result['clean_recipient']]
subject = message.get('subject')
result['subject'] = '' if subject is None else subject.decode('iso-8859-1').encode(self.target_encoding)
raw_date = message.get('date')
if raw_date is not None:
try:
result['date'] = dateutil.parser.parse(raw_date)
except ValueError as valueError:
# todo find a way to deal with these special cases?
# we occasionally get a string the parser won't parse e.g.
# Wed, 17 Dec 2008 12:35:42 -0700 (GMT-07:00)
# and we need to drop off the trailing time zone and try to parse again
logging.warn('%s %s %s', raw_date, valueError, current_file)
pieces = str(raw_date).split('(')
result['date'] = dateutil.parser.parse(pieces[0])
else:
# todo add special code to handle these?
logging.warn('no date: %s ', message)
text_part = message.text_part
if text_part is not None and arg_process_text_part:
charset = text_part.charset
payload = text_part.get_payload()
if charset is not None:
try:
body = payload.decode(charset, 'ignore').encode(self.target_encoding)
except LookupError as lookupError:
if text_part.charset == 'iso-8859-8-i':
body = payload.decode('iso-8859-8', 'ignore').encode(self.target_encoding)
else:
body = payload.decode('utf-8', 'ignore').encode(self.target_encoding)
logging.warn('lookup error %s', lookupError)
else:
body = payload.decode('utf-8', 'ignore').encode(self.target_encoding)
result['body'] = body
short_file_name = os.path.basename(current_file)
result['kmeans_cluster'] = arg_kmeans_cluster_dictionary[short_file_name]
elif message.html_part is not None and arg_process_html_part:
payload = message.html_part.part.get_payload()
payload_text = bs4.BeautifulSoup(payload, 'lxml').get_text().strip()
charset = message.html_part.charset if message.html_part.charset is not None else 'utf-8'
result['body'] = payload_text.decode(charset, 'ignore').encode(self.target_encoding)
elif arg_process_both_empty:
logging.warn('both text_part and html_part are None: %s', current_file)
else:
logging.warn('not processing %s', current_file)
if 'body' in result.keys():
if len(result['body']) == 0:
result['empty_body'] = True
if 'Message-Id' in message.keys():
result['message-id'] = message['Message-Id']
if 'In-Reply-To' in message.keys():
result['in-reply-to'] = message['In-Reply-To']
if 'References' in message.keys():
result['references'] = message['References'].split(' ')
md5 = hashlib.md5()
with open(current_file, 'rb') as fp:
md5.update(fp.read())
return result, md5.hexdigest()
